CN111325652A - Information embedding method, information extracting method, information embedding device, information extracting device, information embedding equipment and computer readable storage medium - Google Patents
Information embedding method, information extracting method, information embedding device, information extracting device, information embedding equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN111325652A CN111325652A CN201811542446.1A CN201811542446A CN111325652A CN 111325652 A CN111325652 A CN 111325652A CN 201811542446 A CN201811542446 A CN 201811542446A CN 111325652 A CN111325652 A CN 111325652A
- Authority
- CN
- China
- Prior art keywords
- screenshot
- information
- watermark information
- embedding
- watermark
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0021—Image watermarking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2201/00—General purpose image data processing
- G06T2201/005—Image watermarking
- G06T2201/0065—Extraction of an embedded watermark; Reliable detection
Abstract
The present disclosure provides an information embedding method, an information extracting method, an information embedding device, an information extracting device, an information embedding apparatus, an information extracting apparatus, and a computer-readable storage medium, including: acquiring a screenshot corresponding to a current display page according to a screenshot instruction sent by a user; acquiring an attribute record corresponding to a current display page; and determining watermark information according to the attribute record, embedding the watermark information into the screenshot, and sending the screenshot embedded with the watermark information so that the equipment receiving the screenshot extracts the watermark information. According to the scheme provided by the disclosure, when a user uses the user terminal to perform screenshot, the user side can generate the watermark according to the attribute record corresponding to the page, and the watermark is embedded into the screenshot, so that the screenshot carries key information of the page when the user sends the screenshot. The device receiving the screenshot can extract the watermark information included in the screenshot so as to obtain the key information of the page, and if the device receiving the screenshot is a customer service end, the customer service end can automatically obtain the key information corresponding to the screenshot sent by the user, so that the processing efficiency of the customer service can be improved.
Description
Technical Field
The present disclosure relates to information processing technologies, and in particular, to an information embedding method, an information extracting method, an information embedding apparatus, an information extracting apparatus, and a computer-readable storage medium.
Background
With the development of the mobile internet, the network platform is more and more widely applied. Network platforms can provide online or offline services to users, and meanwhile, in order to improve user experience, many network platforms are provided with customer service, such as artificial customer service or artificial intelligence customer service.
When consultation, complaint and the like occur, the user can send order or commodity information to the customer service, and the customer service can process the information according to the data provided by the user. At present, many users log in a network platform by using mobile terminals and upload information to customer service in a screenshot mode. This approach is convenient for the user, but inconvenient for the customer service to extract useful information from.
Therefore, in the prior art, the user sends information to the customer service in a screenshot mode, so that the problem of consultation is not conveniently handled by the customer service when the user communicates with the customer service.
Disclosure of Invention
The disclosure provides an information embedding method, an information extracting method, an information embedding device, an information extracting device, information embedding equipment and a computer readable storage medium, and aims to solve the problem of low efficiency in communication between a user and customer service in the prior art.
A first aspect of the present disclosure is to provide an information embedding method, including:
acquiring a screenshot corresponding to a current display page according to a screenshot instruction sent by a user;
acquiring an attribute record corresponding to the current display page;
and determining watermark information according to the attribute record, embedding the watermark information into the screenshot, and sending the screenshot embedded with the watermark information so that the equipment receiving the screenshot extracts the watermark information.
A second aspect of the present disclosure is to provide an information extraction method, including:
carrying out segmentation processing on the received screenshot according to a preset segmentation mode to obtain a plurality of macro blocks;
performing discrete cosine transform on each macro block, and determining a discrete cosine transform coefficient corresponding to each macro block;
and determining a coefficient matrix according to the discrete cosine transform coefficient, and performing inverse singular value decomposition on the coefficient matrix to obtain watermark information.
A third aspect of the present disclosure is to provide an information embedding apparatus, including:
the first acquisition module is used for acquiring a screenshot corresponding to the current display page according to a screenshot instruction sent by a user;
the second acquisition module is used for acquiring the attribute record corresponding to the current display page;
and the embedding module is used for determining watermark information according to the attribute record, embedding the watermark information into the screenshot, and sending the screenshot embedded with the watermark information so that the equipment receiving the screenshot extracts the watermark information.
A fourth aspect of the present disclosure is to provide an information extraction apparatus, including:
the segmentation module is used for segmenting the received screenshot according to a preset segmentation mode to obtain a plurality of macro blocks;
the transformation module is used for performing discrete cosine transformation on each macro block and determining a discrete cosine transformation coefficient corresponding to each macro block;
and the extraction module is used for determining a coefficient matrix according to the discrete cosine transform coefficient and carrying out inverse singular value decomposition on the coefficient matrix to obtain watermark information.
A fifth aspect of the present disclosure is to provide an electronic apparatus, comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the information embedding method of the first aspect or the information extraction method of the second aspect.
A sixth aspect of the present disclosure is to provide a computer-readable storage medium having stored thereon a computer program which is executed by a processor to implement the information embedding method or the information extraction method of the second aspect as described above.
The information embedding and extracting method, device and equipment and the computer readable storage medium provided by the disclosure have the technical effects that:
the information embedding and extracting method, device, equipment and computer readable storage medium provided by the disclosure comprise: acquiring a screenshot corresponding to a current display page according to a screenshot instruction sent by a user; acquiring an attribute record corresponding to a current display page; and determining watermark information according to the attribute record, embedding the watermark information into the screenshot, and sending the screenshot embedded with the watermark information so that the equipment receiving the screenshot extracts the watermark information. According to the information embedding and extracting method and device, the equipment and the computer readable storage medium, when a user uses a user terminal to capture a picture, the user side can generate a watermark according to the attribute record corresponding to the page, and the watermark is embedded into the picture capture, so that when the user sends the picture capture, the picture capture carries key information of the page. The device receiving the screenshot can extract watermark information included in the screenshot so as to obtain page key information, for example, the device receiving the screenshot is a customer service end, the customer service end can automatically obtain the key information corresponding to the screenshot sent by a user, the customer service is not required to identify the screenshot, and therefore the processing efficiency of the customer service can be improved.
Drawings
FIG. 1 is a flow chart illustrating an information embedding method according to an exemplary embodiment of the present invention;
FIG. 2 is a flow chart illustrating an information embedding method according to another exemplary embodiment of the present invention;
fig. 2A is a diagram illustrating watermark information according to an exemplary embodiment of the present invention;
fig. 2B is an encrypted watermark information according to an exemplary embodiment of the present invention;
FIG. 3 is a flow chart illustrating an information extraction method according to an exemplary embodiment of the invention;
FIG. 4 is a block diagram illustrating an information embedding apparatus according to an exemplary embodiment of the present invention;
fig. 5 is a block diagram illustrating an information extraction apparatus according to an exemplary embodiment of the present invention;
fig. 6 is a block diagram illustrating an information embedding apparatus according to an exemplary embodiment of the present invention.
Detailed Description
In some network platforms, when a user communicates with a customer service, the user usually notifies the customer service information, such as order information, commodity information, etc., in a screenshot manner, so that the user can quickly convey information to be output to the customer service. However, for the customer service, it is necessary to obtain relevant information from the picture, and especially when recording or querying according to the information is needed, it is also necessary to identify the information included in the picture, and even to manually enter the information, which results in low efficiency of the customer service for providing service to the user.
The embodiment of the invention can acquire the key information of the page corresponding to the user screenshot and embed the key information into the screenshot in a watermark form, so that the customer service end can automatically extract the key information included in the screenshot without identifying the content in the screenshot by the customer service.
Fig. 1 is a flowchart illustrating an information embedding method according to an exemplary embodiment of the present invention.
As shown in fig. 1, the information embedding method provided by this embodiment includes:
The scheme provided by this embodiment can be executed by a system composed of a user side and a customer service side, and step 101 can be executed by the user side. The user side refers to a terminal device used by the user side, the customer service side refers to a terminal device used by the customer service side, and the customer service can be an artificial customer service or an artificial intelligent customer service. The user side can be connected with the customer service side through a network, and the user side and the customer service side can interact with each other. The user side and the customer service side are both electronic devices with computing functions, and the user side can be further provided with input devices for receiving user operation instructions, such as a touch screen, entity keys and the like.
When the user communicates with the customer service through the user side, the information to be expressed can be input through the input device of the user side, the input information is sent to the customer service side through the user side, and after the customer service side receives the information, the information can be processed by corresponding customer service personnel or artificial intelligence customer service.
Specifically, when communicating with the customer service, the user may input text information or picture information for expressing his/her own meaning, for example, may input "whether the piece of clothing fits the current season", and in order for the customer service to determine which piece of clothing he/she wants to know, the user may also screenshot the commodity picture and send the screenshot to the customer service. In addition, in some cases, the user needs to send the order number to the customer service, generally, the order number is formed by a long string of numbers and/or letters, and if the user manually inputs the order number, the user may need to record the order number by means of other tools and then input the order number in an interface communicated with the customer service, which causes great inconvenience.
Furthermore, when the user captures the screen, the user can display the page needing to be captured on the interface of the user end, adjust the page, display the content needing to be captured on the interface of the user end, and then send a capture instruction to the user end, so that the terminal executes capture operation.
In practical application, a user can send a screenshot instruction to a user side in a mode of operating a touch screen or an entity key. The screenshot instruction may be a double-click screen, or may be a screenshot tool key that is displayed in a suspended manner in the interface by pressing a menu key and a volume key at the same time, and the screenshot instruction may include various forms, which is not limited in this embodiment.
After receiving a screenshot instruction sent by a user, the user side performs screenshot operation on a page currently displayed by the user side, so that a screenshot is obtained. The specific screenshot operation is the same as in the prior art.
And 102, acquiring an attribute record corresponding to the current display page.
Specifically, the attribute records are used for storing information of pages in the network platform, and the attribute records of each page are not identical. For example, for a product introduction page, the attribute record may include information such as a product identifier and a product price, and for an order display page, the attribute record may include information such as an order number and an account number of a purchasing user. The attribute record may be referred to as a cookie, with different pages having corresponding cookies.
Furthermore, the network platform can have a large number of pages, and a user can operate the user side and enter each page, so that the user side can display the pages, and the user side can load cookies corresponding to the pages in the display process.
In practical application, the user can execute step 102, and the user can directly read the attribute record corresponding to the current display page. For example, a cookie for the currently loaded page may be read. Some key information of the page is stored in the cookie of the page, and specifically, which information is set in the cookie can be determined according to requirements, which is not limited in this embodiment.
And 103, determining watermark information according to the attribute record, embedding the watermark information into the screenshot, and sending the screenshot embedded with the watermark information so that the equipment receiving the screenshot extracts the watermark information.
After the user side obtains the attribute record of the page, the watermark information can be determined according to the attribute record. Because the carrier in which the watermark is embedded is a picture, the attribute record can be converted into a matrix form, and then the matrix is embedded into the screenshot. The retrieved property record may be converted to binary and the watermark matrix determined based on the property record in the second level system.
Specifically, in order to improve the security performance of the watermark, the watermark information can be encrypted first, and then the encrypted watermark is embedded into the screenshot, so that malicious use of the watermark information by a person can be avoided.
Further, for pictures, there may be three channels of Y, Cb, and Cr, which are a kind of color space, and are usually used in video continuous processing in movies or digital camera systems. Cb. Cr is a concentration offset component of blue and red, and Y is so-called lumen (luminance), which represents the concentration of light and is nonlinear, and gamma correction (gamma correction) encoding processing is used. In the method provided by this embodiment, the Y component in the screenshot may be extracted, and then the watermark information may be embedded in the Y component information.
In practical application, the extracted Y component information of the screenshot can also be represented by a matrix, the watermark matrix and the Y component matrix are processed, the watermark matrix can be embedded into the Y component matrix, and the screenshot is restored according to the Y component information embedded with the watermark, so that the screenshot embedded with the page attribute record can be obtained. The user can send the screenshot to the customer service through the user side, and the customer service side can extract the embedded watermark information from the screenshot, so that the key information sent by the user can be quickly acquired. In addition, in some application scenarios, because the picture information is easy to be tampered, the screenshot provided by the user cannot be used as an evidence, but in the scheme provided by this embodiment, the key information of the page is automatically obtained and embedded into the screenshot, and the user cannot tamper the embedded information by himself, so that the watermark extracted by the customer service end has high reliability and can be used as an evidence.
After the customer service end receives the screenshot, the screenshot can be processed to extract the watermark information therein, and the specific processing process can be the reverse process of embedding the watermark. The customer service end can also display the extracted information to the customer service, so that the customer service can conveniently process the problems inquired by the user, and the processing efficiency is improved.
The method provided by the present embodiment is used for transmitting information, and is performed by a device provided with the method provided by the present embodiment, and the device is generally implemented in a hardware and/or software manner.
The information embedding method provided by the embodiment comprises the following steps: acquiring a screenshot corresponding to a current display page according to a screenshot instruction sent by a user; acquiring an attribute record corresponding to a current display page; and determining watermark information according to the attribute record, embedding the watermark information into the screenshot, and sending the screenshot embedded with the watermark information so that the equipment receiving the screenshot extracts the watermark information. According to the method provided by the embodiment, when the user uses the user terminal to perform screenshot, the user side can generate the watermark according to the attribute record corresponding to the page, and the watermark is embedded into the screenshot, so that the screenshot carries key information of the page when the user sends the screenshot. The device receiving the screenshot can extract watermark information included in the screenshot so as to obtain page key information, for example, the device receiving the screenshot is a customer service end, the customer service end can automatically obtain the key information corresponding to the screenshot sent by a user, the customer service is not required to identify the screenshot, and therefore the processing efficiency of the customer service can be improved.
Fig. 2 is a flowchart illustrating an information embedding method according to another exemplary embodiment of the present invention.
As shown in fig. 2, the information embedding method provided in this embodiment includes:
Since the attribute information of the page is more, the attribute record may be set with an identifier corresponding to each information, for example, the product identification number may be represented by a product ID, and the product Price may be represented by Price. Specifically, some information in the attribute records can improve communication between the user and the customer service, and some information has no meaning. Data which are meaningful for the customer service to communicate with the user can be selected from the attribute records, and the identification corresponding to the data is determined as the preset identification, so that when information is embedded, target data corresponding to the preset identification can be obtained, namely, the target data are embedded into the screenshot.
Further, the target data is data capable of improving the communication efficiency between the customer service and the user, and therefore, watermark information can be generated according to the data. The watermark provided by this embodiment may be a digital watermark, and may determine a binary value of the target data, where the binary value may be one-dimensional, and then rewrites the one-dimensional binary value into a matrix form according to a certain rule, thereby obtaining two-dimensional watermark information.
In practical application, the carrier for embedding the watermark information is a picture, specifically a Y component in the picture, and the Y component is two-dimensional data, so that the watermark is adjusted to a two-dimensional form and embedded. If the watermark information is not rewritten into a two-dimensional form, further processing of the watermark information, such as block embedding, is required in the embedding process.
Fig. 2A illustrates watermark information according to an exemplary embodiment of the present invention.
Fig. 2B shows encrypted watermark information according to an exemplary embodiment of the present invention.
In order to improve the security of the watermark information, prevent a malicious user from illegally acquiring the screenshot in which the watermark is embedded, and extract the key information embedded therein, the method provided by this embodiment may further perform encryption processing on the watermark information. Even if a malicious user extracts watermark information, the key information in the watermark information cannot be recovered, and the safety can be improved. As shown in fig. 2A and 2B, it is not possible to directly confirm what content is specifically included in the encrypted watermark information.
Specifically, the watermark information may be scrambled based on the Arnold transformation, so as to encrypt the watermark information. Specifically, the positions of the pixel values having strong correlation may be adjusted so that the pixel positions are scrambled by the correlation. The Arnold transform can be expressed as:
wherein a and b are positive integers and are preset scrambling coefficients. (x, y) and (x ', y') are the positions of the pre-and post-scrambling pixels, respectively. N is the image size of the embedded carrier (screenshot). By the above method, the positions of the pixel values can be adjusted, so that the original relevance between the pixel values is disturbed.
Specifically, the encrypted watermark can be embedded into the screenshot, and the user can operate the user side to send the screenshot embedded with the encrypted watermark to the customer service side.
Further, in the embedding process, the screenshot may be segmented according to a preset segmentation mode to obtain a plurality of macroblocks. And then performing Discrete Cosine Transform (DCT) on each macro block to determine a discrete cosine transform coefficient corresponding to each macro block. The encrypted watermark information is then embedded in the discrete cosine transform coefficients. By discrete cosine transform, a picture can be converted into a matrix form.
When the screenshot is divided, the screenshot may be firstly cut into a plurality of strips in the horizontal direction, each strip is called a slice, each slice is then cut into a plurality of blocks in the vertical direction, which are called macro blocks, and the macro blocks are basic units of image compression. The color image of each macroblock can be represented by 1 luminance signal Y and two color difference signals Cb, Cr, or each macroblock is divided into three layers, one luminance Y layer and two chrominance layers (Cb, Cr, respectively), collectively referred to as a macroblock.
Specifically, since human eyes have high sensitivity to luminance, each macro block may be further divided, for example, into 4 small blocks, and the luminance value of each small block may be extracted. When performing Discrete Cosine Transform (DCT) on each macro block, discrete cosine transform may be performed on a luminance value corresponding to each macro block.
Further, Discrete Cosine Transform (DCT) is a digital processing method used for data processing. DCT is one of a plurality of digital transformation methods, which is a method of transforming a spatial domain image into a frequency domain for analysis. Because the basis vector formed by the transformation kernel of the DCT is irrelevant to the image content and the transformation kernel can be separated, the two-dimensional DCT can be completed by two times of one-dimensional DCT, so that the difficulty of mathematical operation is greatly simplified, and the DCT coding is widely applied by matching with other found rapid algorithms. The DCT is applied to image data compression, so that the digital information representing the image brightness (or chroma) level can be reduced, and the purpose of data compression is achieved. The DCT can be used to code the image, and the position of the image detail can be found in the coding transformation process, so as to eliminate or omit the part which is not sensitive to vision, but highlight the sensitive part of vision, and the image is transmitted and valued by selecting the main data.
In practical application, the encrypted watermark information can be embedded into the discrete cosine transform coefficient, so that the brightness value of the embedded information is obtained, and the screenshot is restored based on the brightness value, so that the final screenshot is obtained.
In order to reduce the influence of the watermark on the picture, watermark information can be embedded into an intermediate frequency coefficient in discrete cosine transform coefficients. Meanwhile, in order to better solve the problem of compression resistance of the watermark-embedded picture, singular value decomposition conversion can be performed on the discrete cosine transform coefficient corresponding to each macro block, and then embedding operation is performed.
Specifically, a first matrix is determined according to an intermediate frequency coefficient in a discrete cosine transform coefficient, and orthogonal transformation is performed on the first matrix to obtain a coefficient matrix; performing singular value decomposition on the coefficient matrix to obtain a singular value matrix; and embedding the encrypted watermark information into the singular value matrix.
Furthermore, an intermediate frequency coefficient can be determined in the discrete cosine transform coefficient, and then the first matrix is determined according to the intermediate frequency coefficient. And then carrying out orthogonal transformation (APBT transformation) on the first matrix to obtain a coefficient matrix, and then carrying out singular value decomposition (SVD decomposition) on the coefficient matrix to obtain a singular value matrix. Assuming that the coefficient matrix is D, the singular value decomposition yields:
SVD(D)＝[U1,S1,V1]
in practical application, the matrix D can be decomposed into U1、S1、V1The three sub-matrices, wherein U1Is a U-order matrix, V1Is a V-order matrix, S1(singular value)Matrix) is a U × V sized matrix.
Wherein S is1Can be expressed as:
the matrix obtained by the watermark information can be represented as W, and the matrix corresponding to the watermark information can be embedded into the singular value matrix to obtain a new matrix, wherein the new matrix S1'＝S1+ α W, α is the scale factor, determining the new matrix S1The manner of' may be:
in practical application, the transformed new matrix can be used as the brightness value of the screenshot, and the inverse discrete cosine transform is performed on the new matrix to recover the pixel block of the image and send the recovered screenshot to the customer service end.
Fig. 3 is a flowchart illustrating an information extraction method according to an exemplary embodiment of the present invention.
The method provided by the embodiment comprises the steps of extracting the watermark information, and the steps are realized by the customer service end. The specific process of extracting the watermark information can be determined according to the process of embedding the watermark information, and the watermark information can be restored by adopting the inverse process of the embedding process.
The user side can send the screenshot of the embedded watermark to the customer service side, and after the customer service side receives the screenshot, the watermark information included in the screenshot can be extracted.
Specifically, the customer service end may perform segmentation processing on the received screenshot according to a preset segmentation mode, which is the same as a segmentation mode for the screenshot when the client embeds watermark information in the screenshot. For example, the screenshot may first be cut into several strips in the horizontal direction, each strip being called a slice, and each slice is then cut into several blocks, i.e. macroblocks, in the vertical direction.
Further, if the watermark information is embedded in the brightness value Y of the screenshot, the brightness value in each macro block can be extracted, and then discrete cosine transform is performed on the brightness value to obtain a discrete cosine transform coefficient corresponding to each macro block, so that the picture is converted into a matrix.
In practical application, if the watermark information is embedded in the intermediate frequency coefficient of the discrete cosine transform coefficients in the embedding process, the intermediate frequency coefficient of the discrete cosine transform coefficients also needs to be extracted. Watermark information is then extracted among these coefficients.
If orthogonal transformation is performed on the discrete cosine transform coefficient in the process of embedding the watermark information, a matrix can be determined according to the intermediate frequency coefficient, and then the matrix is subjected to orthogonal transformation to obtain a coefficient matrix. If the watermark information embedding process includes singular value decomposition, in the extraction process, inverse SVD change, namely inverse singular value decomposition, needs to be performed on the coefficient matrix to obtain the watermark information.
Specifically, the quotient can be calculated by dividing α by the parameters in the resulting matrix to obtain the watermark information, i.e., S1＝1′/α。
Further, since the extracted watermark information may include noise, a threshold value may be set to remove the noise. The extracted data can be compared with a threshold value, so that accurate watermark information is further extracted.
In the method provided by the embodiment, the customer service end can extract the information embedded in the screenshot, so that key information required in the process of communicating with the customer can be quickly acquired, and the communication efficiency between the customer service and the user can be improved.
Fig. 4 is a block diagram illustrating an information embedding apparatus according to an exemplary embodiment of the present invention.
As shown in fig. 4, the information embedding apparatus provided in this embodiment includes:
the first obtaining module 41 is configured to obtain a screenshot corresponding to a current display page according to a screenshot instruction sent by a user;
a second obtaining module 42, configured to obtain an attribute record corresponding to the current display page;
and an embedding module 43, configured to determine watermark information according to the attribute record, embed the watermark information in the screenshot, and send the screenshot in which the watermark information is embedded, so that a device receiving the screenshot extracts the watermark information.
The information embedding device provided by the embodiment comprises: the first acquisition module is used for acquiring a screenshot corresponding to the current display page according to a screenshot instruction sent by a user; the second acquisition module is used for acquiring the attribute record corresponding to the current display page; and the embedding module is used for determining the watermark information according to the attribute record, embedding the watermark information into the screenshot, and sending the screenshot embedded with the watermark information so that the equipment receiving the screenshot extracts the watermark information. According to the device provided by the embodiment, when a user uses the user terminal to perform screenshot, the user side can generate the watermark according to the attribute record corresponding to the page, and the watermark is embedded into the screenshot, so that the screenshot carries key information of the page when the user sends the screenshot. The device receiving the screenshot can extract watermark information included in the screenshot so as to obtain page key information, for example, the device receiving the screenshot is a customer service end, the customer service end can automatically obtain the key information corresponding to the screenshot sent by a user, the customer service is not required to identify the screenshot, and therefore the processing efficiency of the customer service can be improved.
The specific principle and implementation of the information embedding apparatus provided in this embodiment are similar to those of the embodiment shown in fig. 1, and are not described herein again.
On the basis of the above embodiment, the root embedding module 43 is specifically configured to:
acquiring target data with a preset identifier in the attribute record;
and determining the watermark information according to the target data.
The root embedding module 43 is specifically configured to:
and encrypting the watermark information to obtain encrypted watermark information, and embedding the encrypted watermark information into the screenshot.
The root embedding module 43 is specifically configured to:
the screenshot is divided according to a preset dividing mode to obtain a plurality of macro blocks;
performing discrete cosine transform on each macro block, and determining a discrete cosine transform coefficient corresponding to each macro block;
and embedding the encrypted watermark information into the discrete cosine transform coefficient.
The root embedding module 43 is specifically configured to:
determining a first matrix according to an intermediate frequency coefficient in the discrete cosine transform coefficient, and performing orthogonal transform on the first matrix to obtain a coefficient matrix;
performing singular value decomposition on the coefficient matrix to obtain a singular value matrix;
and embedding the encrypted watermark information into the singular value matrix.
Fig. 5 is a block diagram illustrating an information extraction apparatus according to an exemplary embodiment of the present invention.
As shown in fig. 5, the information extraction device provided in this embodiment includes:
a dividing module 51, configured to divide the received screenshot according to a preset dividing manner to obtain multiple macroblocks;
a transform module 52, configured to perform discrete cosine transform on each macroblock, and determine a discrete cosine transform coefficient corresponding to each macroblock;
and the extracting module 53 is configured to determine a coefficient matrix according to the discrete cosine transform coefficient, and perform inverse singular value decomposition on the coefficient matrix to obtain watermark information.
The information extraction device provided by the embodiment comprises: the segmentation module is used for segmenting the received screenshot according to a preset segmentation mode to obtain a plurality of macro blocks; the transformation module is used for carrying out discrete cosine transformation on each macro block and determining a discrete cosine transformation coefficient corresponding to each macro block; and the extraction module is used for determining a coefficient matrix according to the discrete cosine transform coefficient and carrying out inverse singular value decomposition on the coefficient matrix to obtain the watermark information. The extraction device can extract the information embedded in the screenshot, and can quickly acquire key information required in the process of communicating with the customer, so that the communication efficiency between the customer service and the user is improved.
The specific principle and implementation of the apparatus provided in this embodiment are similar to those of the embodiment shown in fig. 3, and are not described herein again.
Fig. 6 is a block diagram illustrating an information embedding apparatus according to an exemplary embodiment of the present invention.
As shown in fig. 6, the information embedding apparatus provided by the present embodiment includes:
a memory 61;
a processor 62; and
a computer program;
wherein the computer program is stored in the memory 61 and configured to be executed by the processor 62 to implement any one of the information embedding methods described in fig. 1-2 or the information extraction method described in fig. 3.
The present embodiments also provide a computer-readable storage medium, having stored thereon a computer program,
the computer program is executed by a processor to implement any one of the information embedding methods described in fig. 1-2 or the information extraction method described in fig. 3.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An information embedding method, comprising:
acquiring a screenshot corresponding to a current display page according to a screenshot instruction sent by a user;
acquiring an attribute record corresponding to the current display page;
and determining watermark information according to the attribute record, embedding the watermark information into the screenshot, and sending the screenshot embedded with the watermark information so that the equipment receiving the screenshot extracts the watermark information.
2. The method of claim 1, wherein determining watermark information based on the attribute record comprises:
acquiring target data with a preset identifier in the attribute record;
and determining the watermark information according to the target data.
3. The method of claim 1, wherein the embedding the watermark information into the screenshot comprises:
and encrypting the watermark information to obtain encrypted watermark information, and embedding the encrypted watermark information into the screenshot.
4. The method of claim 3, wherein embedding the encrypted watermark information in the screenshot comprises:
the screenshot is divided according to a preset dividing mode to obtain a plurality of macro blocks;
performing discrete cosine transform on each macro block, and determining a discrete cosine transform coefficient corresponding to each macro block;
and embedding the encrypted watermark information into the discrete cosine transform coefficient.
5. The method of claim 4, wherein embedding the encrypted watermark information into the discrete cosine transform coefficients comprises:
determining a first matrix according to an intermediate frequency coefficient in the discrete cosine transform coefficient, and performing orthogonal transform on the first matrix to obtain a coefficient matrix;
performing singular value decomposition on the coefficient matrix to obtain a singular value matrix;
and embedding the encrypted watermark information into the singular value matrix.
6. An information extraction method, comprising:
carrying out segmentation processing on the received screenshot according to a preset segmentation mode to obtain a plurality of macro blocks;
performing discrete cosine transform on each macro block, and determining a discrete cosine transform coefficient corresponding to each macro block;
and determining a coefficient matrix according to the discrete cosine transform coefficient, and performing inverse singular value decomposition on the coefficient matrix to obtain watermark information.
7. An information embedding apparatus, comprising:
the first acquisition module is used for acquiring a screenshot corresponding to the current display page according to a screenshot instruction sent by a user;
the second acquisition module is used for acquiring the attribute record corresponding to the current display page;
and the embedding module is used for determining watermark information according to the attribute record, embedding the watermark information into the screenshot, and sending the screenshot embedded with the watermark information so that the equipment receiving the screenshot extracts the watermark information.
8. An information extraction apparatus characterized by comprising:
the segmentation module is used for segmenting the received screenshot according to a preset segmentation mode to obtain a plurality of macro blocks;
the transformation module is used for performing discrete cosine transformation on each macro block and determining a discrete cosine transformation coefficient corresponding to each macro block;
and the extraction module is used for determining a coefficient matrix according to the discrete cosine transform coefficient and carrying out inverse singular value decomposition on the coefficient matrix to obtain watermark information.
9. An electronic device, comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the information embedding method of any one of claims 1 to 5 or the information extraction method of claim 6.
10. A computer-readable storage medium, having stored thereon a computer program,
the computer program is executed by a processor to implement the information embedding method of any one of claims 1 to 5 or the information extraction method of claim 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811542446.1A CN111325652A (en) | 2018-12-17 | 2018-12-17 | Information embedding method, information extracting method, information embedding device, information extracting device, information embedding equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811542446.1A CN111325652A (en) | 2018-12-17 | 2018-12-17 | Information embedding method, information extracting method, information embedding device, information extracting device, information embedding equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111325652A true CN111325652A (en) | 2020-06-23 |
Family
ID=71172338
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811542446.1A Pending CN111325652A (en) | 2018-12-17 | 2018-12-17 | Information embedding method, information extracting method, information embedding device, information extracting device, information embedding equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111325652A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113032707A (en) * | 2021-03-25 | 2021-06-25 | 成都新希望金融信息有限公司 | Method and device for generating webpage screenshot and electronic equipment |
| CN113542206A (en) * | 2020-11-27 | 2021-10-22 | 腾讯科技（深圳）有限公司 | Image processing method and device and computer readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105631359A (en) * | 2015-12-23 | 2016-06-01 | 北京奇虎科技有限公司 | Control method and device of webpage operation |
| CN105701758A (en) * | 2016-01-13 | 2016-06-22 | 华南理工大学 | Digital watermarking image generation method based on graphic code and apparatus thereof |
| CN108924029A (en) * | 2018-04-11 | 2018-11-30 | 阿里巴巴集团控股有限公司 | A kind of method and device that customer service data are sent |
| CN108984777A (en) * | 2018-07-25 | 2018-12-11 | 北京京东尚科信息技术有限公司 | Customer service method, apparatus and computer readable storage medium |
| CN108985081A (en) * | 2018-07-06 | 2018-12-11 | 泰康保险集团股份有限公司 | A kind of watermark encrypting method, apparatus, medium and electronic equipment |
-
2018
- 2018-12-17 CN CN201811542446.1A patent/CN111325652A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105631359A (en) * | 2015-12-23 | 2016-06-01 | 北京奇虎科技有限公司 | Control method and device of webpage operation |
| CN105701758A (en) * | 2016-01-13 | 2016-06-22 | 华南理工大学 | Digital watermarking image generation method based on graphic code and apparatus thereof |
| CN108924029A (en) * | 2018-04-11 | 2018-11-30 | 阿里巴巴集团控股有限公司 | A kind of method and device that customer service data are sent |
| CN108985081A (en) * | 2018-07-06 | 2018-12-11 | 泰康保险集团股份有限公司 | A kind of watermark encrypting method, apparatus, medium and electronic equipment |
| CN108984777A (en) * | 2018-07-25 | 2018-12-11 | 北京京东尚科信息技术有限公司 | Customer service method, apparatus and computer readable storage medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113542206A (en) * | 2020-11-27 | 2021-10-22 | 腾讯科技（深圳）有限公司 | Image processing method and device and computer readable storage medium |
| CN113542206B (en) * | 2020-11-27 | 2023-07-04 | 腾讯科技（深圳）有限公司 | Image processing method, device and computer readable storage medium |
| CN113032707A (en) * | 2021-03-25 | 2021-06-25 | 成都新希望金融信息有限公司 | Method and device for generating webpage screenshot and electronic equipment |
| CN113032707B (en) * | 2021-03-25 | 2023-01-31 | 成都新希望金融信息有限公司 | Method and device for generating webpage screenshot and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ra et al. | P3: Toward {Privacy-Preserving} Photo Sharing | |
| Thai et al. | Statistical model of quantized DCT coefficients: Application in the steganalysis of Jsteg algorithm | |
| Sadek et al. | Video steganography: a comprehensive review | |
| Saber et al. | Watermarking System for Medical Images Using Optimization Algorithm | |
| Cedillo-Hernández et al. | Robust hybrid color image watermarking method based on DFT domain and 2D histogram modification | |
| US8355525B2 (en) | Parallel processing of digital watermarking operations | |
| Jenifer et al. | LSB approach for video steganography to embed images | |
| Fayyaz et al. | An improved surveillance video forgery detection technique using sensor pattern noise and correlation of noise residues | |
| CN110248177B (en) | Image data processing method and device | |
| CN115002293B (en) | Privacy confidentiality method, system and storage medium based on thumbnail format reservation | |
| CN112468715A (en) | Video tracing system and video tracing method | |
| KR20110058062A (en) | Network photographing apparatus having a partial encryption function | |
| CN111325652A (en) | Information embedding method, information extracting method, information embedding device, information extracting device, information embedding equipment and computer readable storage medium | |
| Juarez-Sandoval et al. | Digital image ownership authentication via camouflaged unseen-visible watermarking | |
| Altun et al. | Optimal spread spectrum watermark embedding via a multistep feasibility formulation | |
| Siddiqui et al. | Chaos-based video steganography method in discrete cosine transform domain | |
| Chen et al. | An improved blind watermarking method facing dual color images based on Hadamard transform | |
| Jiang et al. | A high capacity steganographic method based on quantization table modification and F5 algorithm | |
| Liang et al. | Invertible color-to-grayscale conversion using lossy compression and high-capacity data hiding | |
| Zhang et al. | In-camera JPEG compression detection for doubly compressed images | |
| Tulsani et al. | A novel steganographic model for securing binary images | |
| CN113536341A (en) | Data hiding method, device, equipment and computer readable storage medium | |
| Kaimal et al. | A modified anti-forensic technique for removing detectable traces from digital images | |
| Durdu | A new reversible low-distortion steganography method that hides images into RGB images with low loss | |
| Fkirin et al. | A new approach for colored watermarking image into gray scale image using wavelet fusion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |